CN106169001B - A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching - Google Patents
A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching Download PDFInfo
- Publication number
- CN106169001B CN106169001B CN201610543226.5A CN201610543226A CN106169001B CN 106169001 B CN106169001 B CN 106169001B CN 201610543226 A CN201610543226 A CN 201610543226A CN 106169001 B CN106169001 B CN 106169001B
- Authority
- CN
- China
- Prior art keywords
- engine
- predicted
- aero
- life
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention proposes a kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching, solve the problems, such as that aero-engine complete machine remaining life is difficult to Accurate Prediction, firstly, the life-cycle history degraded data using same model engine constructs degradation modes dictionary.Secondly, about subtracting to the data progress sensor selection of engine to be predicted and state parameter dimension.Again, by engine to be predicted decline track and degeneration dictionary in reference engine decline track progress Graphic Pattern Matching, obtain engine to be predicted life estimation and with each similarity with reference to engine.Finally, obtaining the remaining life of engine to be predicted by similitude weighted strategy.Method proposed by the present invention can accurately predict the remaining life of aero-engine, and life prediction has very important significance for the maintenance and maintenance of engine.
Description
Technical field
The present invention relates to the technical fields of aero-engine predicting residual useful life, and in particular to one kind is joined based on gas circuit performance
The aero-engine complete machine method for predicting residual useful life of number Graphic Pattern Matching.
Background technique
With modern Aviation industrial expansion, all kinds of aircrafts be will be used wider and wider, the carrying capacity of single rack aircraft
Increasingly stronger, consequent is the requirements at the higher level to aircraft reliability and safety.Safety, reliability and economy are boats
The three big factors and measured engine system that the relevant departments such as empty manufacturers of engines, maintenance factory and airline are concerned about the most
Make horizontal critical index.However, aero-engine is as the most important core component of aircraft, since its structure is complicated, collection
Its stability is caused to be difficult to control at many factors such as high, operating condition is severe are spent.Also, since it serves as the main dynamic of aircraft
Power source often leads to the catastrophic effect of fatal crass once aero-engine breaks down.Therefore, maximum in order to obtain
Economic benefit and safety, how to carry out predicting residual useful life to aero-engine becomes focus and the academia of industry
Research hotspot.
Based on gas circuit performance parameter carry out aero-engine complete machine health status monitoring and life prediction in recent years by
The concern of scholars.However, structure is complicated for aero-engine, performance parameter is many kinds of, has stronger correlation between parameter
Property.In addition, engine works long hours in the complicated rugged environment such as high temperature, high pressure, the parameter of system health status is characterized
It is subjected to the interference of various noises, Accurate Prediction engine complete machine remaining life is very difficult in this background.
Summary of the invention
The technical problem to be solved in the present invention are as follows: be difficult to asking for Accurate Prediction for aero-engine complete machine remaining life
Topic, proposes a kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching.
The technical solution adopted by the present invention are as follows: a kind of aero-engine complete machine based on gas circuit performance parameter Graphic Pattern Matching is surplus
Remaining life-span prediction method, it is characterised in that:
(1) its performance degradation mode is obtained by the gas circuit degraded data of aero-engine life-cycle, and uses more hairs
The degraded data building performance degradation of motivation is referring to dictionary；
(2) the performance degradation mode of aero-engine system is steadily characterized using the envelope polygon of Degradation path；
(3) performance between the two is quantified by reference to the overlapping area of engine and engine degenerate polygon to be predicted
The correlation of deterioration law, and the overlapping area ratio using line segment length than equivalently calculating two polygons；
(4) using the true remaining life of reference engine as the estimated value of engine residual life to be predicted, according to weight
Folded area ratio generates similarity weight, weights these life estimation values to obtain the remaining life of engine to be predicted.
The advantages of the present invention over the prior art are that:
(1), the performance degradation rule in the full longevity degraded data of history is sufficiently excavated based on similarity theory, and applies the rule
Rule estimates that the remaining life of engine to be predicted, precision of prediction is high；
(2), it is influenced by sensor measurement noise etc., the performance degradation track of acquisition often has more burr, is based on
The similitude matching robustness of Euclidean distance is poor, and overlapping area matching can not only guarantee matching precision, but also can be to avoid noise
Interference.
(3), first the remaining life of engine to be predicted is repeatedly estimated, then to estimated value weight it is integrated obtain to
Predict the remaining life of engine, this method has the advantage of integrated study, and algorithm robustness is good.
Detailed description of the invention
Fig. 1 is a kind of aero-engine complete machine predicting residual useful life side based on gas circuit performance parameter Graphic Pattern Matching of the present invention
Method flow chart；
Fig. 2 is that performance degradation polygon extracts schematic diagram；
Fig. 3 is Riemann integral schematic diagram；
Fig. 4 is overlapping areal calculation schematic diagram；
Fig. 5 is optimal area matching principle figure；
Fig. 6 is turbofan gas path component schematic diagram；
Fig. 7 is 21 sensor parameters situations of change of 1# engine；
Fig. 8 is situation of change of the state parameter first principal component with circulation；
Fig. 9 is the estimated result using first 4 with reference to engine data to 1# engine RUL.
Specific embodiment
With reference to the accompanying drawing and specific embodiment further illustrates the present invention.
As shown in Figure 1, a kind of aero-engine complete machine method for predicting residual useful life based on Graphic Pattern Matching, it is main comprising with
Lower step:
The first step constructs engine performance degeneration dictionary.The engine historical data of failure is had been running for by handling,
Obtain the degradation modes dictionary that can be referred to when prediction.Firstly, selection has the sensor parameters for obviously rising or falling trend
To characterize the performance degradation of engine.Dimensionality reduction is carried out to data secondly, about subtracting method using dimension, one-dimensional performance is obtained and moves back
Change curve.Finally, these refer to the Performance Degradation Data of engine according to certain specification storage, used convenient for later retrieval.
Second step, engine data pretreatment to be predicted.Sensor parameters identical with degeneration dictionary are selected, and with equally
Dimension reduction method carry out state parameter dimension and about subtract.
Third step, the Degradation path for referring to engine using polygon matching method matches every and engine to be predicted
Degradation path.Firstly, extracting the upper lower enveloping curve for referring to engine and engine Degradation path to be predicted, their move back is obtained
Change Polygons Representation form.Secondly, it is polygon to match engine degeneration to be predicted in every degenerate polygon with reference to engine
Shape keeps the area of their laps maximum.Finally, calculating the area ratio of overlapping and the estimated value of RUL.
4th step, weighting are integrated.Similarity weight is generated by overlapping area, multiple RUL estimated values are weighted, most
The remaining life of engine to be predicted is obtained eventually.
Specific step is as follows for the 1 aero-engine complete machine method for predicting residual useful life based on Graphic Pattern Matching:
1.1 high dimensional data dimensions about subtract
(1) sensor selects
Aero-engine has a performance state parameter of a large amount of real-time monitoring, and not all state parameter can reflect and be
The performance state of system degrades, such as control amount of some actives etc..Before carrying out life prediction, need to find out with degradation trend
Sensor parameters, as the state index of reflection overall performance, health status to gauging system.
(2) principal component analysis (PCA)
After sensor screens, status monitoring parameter still has very high dimension, this is for follow-up data processing
Unfavorable, thus also need to carry out further about subtracting for parameter dimensions.Here, our Selective principal component analysis methods carry out data
Dimensionality reduction.
Principal component analysis (PCA, Principle Component Analysis) is that a kind of most widely used feature mentions
One of method is taken, it is a kind of statistical method, has been obtained in fields such as signal processing, pattern-recognition, Digital Image Processing
It is widely applied.Principal component analytical method basic thought is the main feature (pivot) extracted in the initial data of space, is subtracted
Few data redundancy so that data are processed in the feature space of a low-dimensional, while keeping the letter of the overwhelming majority of initial data
Breath, to solve the excessively high bottleneck problem of data space dimension.
If aero-engine degenerate state matrix is X, column vector Xk=(x1k,x2k,...,xnk)TState parameter is tieed up for n,
The a certain performance state of engine can be by xkDescription, xkCovariance matrix are as follows:
In formula, N is the hits of degenerate state,For the mean value of each state parameter
Solve RxAll Eigenvalues λi(i=1,2 ..., n) and feature vector vi, by eigenvalue λiAccording to from big to small
Sequence arrangement: λ1>λ2>...>λn, then corresponding feature vector is vi(i=1,2 .., n).Sample xiProject to feature vector
viObtain the corresponding principal component of the direction are as follows:
All Zhang Chengyi n of feature vector tie up orthogonal intersection space, and x projects to the orthogonal intersection space and obtains main point of corresponding n dimension
Amount.Characteristic value corresponding to feature vector is bigger, it reconstruct when contribution it is also bigger, the smaller feature vector of characteristic value weight
Contribution when structure is with regard to smaller.If preceding m principal component is y in orthogonal intersection space1,y2,...,ym, add up variance contribution ratio are as follows:
When the accumulative variance contribution ratio of a few principal component of front is sufficiently large, such as h (m) > 95%, i.e., 95% or more original
Beginning data information is retained in the several principal components in front, can only be taken preceding m (m < n) a principal component to characterize raw information, guaranteed
In the complete situation of information, achieve the purpose that Data Dimensionality Reduction.
1.2 performance degradation polygons extract
Due to the influence of measurement noise etc., reflect the state parameter of system performance degradation usually contained it is biggish at random at
Point, performance sequence is shown as with fluctuation by a relatively large margin, this brings great challenge to follow-up data processing.If not being subject to
Consider directly to carry out operation, then calculated result is highly prone to the influence of these interference, and the robustness of method is poor；According to data
It is the methods of smooth to be filtered, it is be easy to cause the loss of useful degradation information, ' degree ' of filtering is difficult to hold.Therefore, I
The degenerative process of system performance is characterized with degenerate polygon.
As shown in Fig. 2, indicating some performance degradation parameters (such as turbine outlet of aero-engine system with blue curve
Temperature) degenerated curve.It can be seen that the degradation parameter is while there are obvious ascendant trend, with by a relatively large margin
Random disturbances.For the processing work convenient for follow-up data.It extracts the upper lower envelope (red line) of degenerated curve and is allowed to constitute closing
Polygon, to characterize its performance degradation mode.
1.3 Graphic Pattern Matching principles
Sufficiently to illustrate Graphic Pattern Matching principle, we are first simple Jie to the principle of the Riemann integral in calculus theory
It continues.As shown in figure 3, the area for the bent top figure that curve f (x) is surrounded with x-axis can be calculated with Riemann integral.When each rectangle
Height very little, i.e., when n is sufficiently big, the area of enclosed figure is approximately equal to the sum of these rectangular areas.
As shown in figure 4, blue portion and green portion respectively indicate two polygons, area A1And A2.Yl moiety
Indicate the lap of two polygons, area A∩.By horizontal axis N (sufficiently large) equal part, every segment length is △, then each section
Area can be as follows with approximate representation:
In formula, △ divides the length at interval, L1i, L2iAnd L∩iPolygon 1 at respectively i-th of division points, 2 He of polygon
Longitudinal span of overlapping polygon.
The ratio that lap accounts for area of a polygon is respectively
In formula, △ divides the length at interval, L1i, L2iAnd L∩iPolygon 1 at respectively i-th of division points, 2 He of polygon
Longitudinal span of overlapping polygon.
From formula (2) it is found that not needing exact calculate when we want the overlapping degree of two figures of half quantification
Lap and respective area value, overlap ratio can be obtained by the calculating to longitudinal span of polygon at each division points
, it does so and can reduce calculation amount, promote operation efficiency.
When we execute prediction task, core process is by the degenerate polygon of engine to be predicted in reference engine
It is matched on life-cycle polygon, finds and be allowed to utmostly matched time point, the surplus of engine to be predicted can be obtained
Remaining service life.Blue Polygons Representation has gone out the full longevity degenerate polygon with reference to engine in Fig. 5, and green Polygons Representation waits for
Predict the degenerate polygon of engine.For optimal two polygons of matching, by polygon to be predicted on reference polygon,
From rear to advance line slip, and calculate the overlap ratio (A of each slip locations∩/A1), make the maximum sliding step number of overlap ratio be
With an estimated value of the remaining life (RUL) for referring to the engine to be predicted that polygon is predicted.
1.4 integrated weightings
Assuming that there is L respectively to refer to engine, matched by polygon, we obtain L overlapping area ratio and corresponding L
RUL estimated value, with setlP,lR }, l=1,2 ..., L is indicated.To obtain engine residual service life to be predicted, pass through weight
Folded area generates similarity weight.
The integrated purpose of weighting is the life estimation for integrating multiple estimated results and finally obtaining sample to be predicted.It is simplest
Integrated approach is using the weighted sum based on similitude, the then point estimation of engine RUL to be predicted are as follows:
2 experimental verifications
We are proposed using 1 Dui of Dataset of the NASA NASA fanjet data set provided pre-
Survey method carries out validation verification.The data set is by C-MAPSS (Commercial Modular Aero-propulsion
System Simulation) large-scale turbofan simulation model obtains.Model is simulated by the input of 14 parameters
Including five including fan, low-pressure compressor, high-pressure compressor, high-pressure turbine, low-pressure turbine (Fan, LPC, HPC, HPT, LPT)
Big rotary part failure effect and degenerative process, engine simulation model main component schematic diagram are as shown in Figure 6.
Data are run 3 duty parameters (flying height, flight Mach number and throttles of circulation time point by engine difference
Bar angle) 21 sensor monitorings performance parameter composition.Sensor monitor value is to be moved for research module by engine thermal
Power simulation model obtains, and includes noise.Training data includes the multivariate time series sample of the independent same unit of multiple groups, reflection
Each unit is from initially to the change procedure of the life cycle management of failure.The degenerate case of the initial time of each component be with
Machine and unknown, if occur to degenerate and degree of degeneration is different, with the operation of engine, when performance degradation a to threshold value
Rear whole system fail.21 monitoring parameters values for measured engine performance state are as shown in table 1.
1 mode input parameter of table
| Serial number | Description | Symbol |
| 1 | Fuel flow rate | Wf(pps) |
| 2 | Fan efficiency parameter | fan_eff_mod |
| 3 | Fan flow parameter | fan_flow_mod |
| 4 | Fan pressure ratio parameter | fan_PR_mod |
| 5 | Low-pressure compressor efficiency parameters | LPC_eff_mod |
| 6 | Low-pressure compressor flow parameter | LPC_flow_mod |
| 7 | Low-pressure compressor pressure ratio parameter | LPC_PR_mod |
| 8 | High-pressure compressor efficiency parameters | HPC_eff_mod |
| 9 | High-pressure compressor flow parameter | HPC_flow_mod |
| 10 | High-pressure compressor pressure ratio parameter | HPC_PR_mod |
| 11 | High-pressure turbine efficiency parameters | HPT_eff_mod |
| 12 | High-pressure turbine flow parameter | HPT_flow_mod |
| 13 | Low-pressure turbine efficiency parameters | LPT_eff_mod |
| 14 | Low-pressure turbine flow parameter | LPT_flow_mod |
2 monitoring parameters token state of table
The selection of 2.1 sensors
Those monitoring parameters without visible trend are rejected by observing the variation tendency of each sensor parameters, in order to
Follow-up data processing.21 sensor monitoring parameters of 1# engine are as shown in Figure 7 with the increased situation of change of recurring number.
According to Fig. 7 it is found that the monitoring data of sensor 1,5,6,10,16,18 and 19 are increased using recurring number in engine
Value is kept constant in the process, it is impossible to be used in characterizes the performance degradation of system.Therefore, we select the biography with significant degradation trend
This 14 monitoring parameters of sensor 2,3,4,7,8,9,11,12,13,14,15,17,20 and 21 characterize the performance of engine system
It degenerates.
2.2 data normalizations and dimension about subtract
Different monitoring parameters have different dimensions, do not have comparativity between data, need that data are normalized
Processing, initial data is mapped between 0-1, and the specific mapminmax function using Matlab is realized.
Often there is certain linear relationships between higher-dimension monitoring parameters improves and calculates to mitigate computation complexity
Accuracy, we carry out about subtracting for parameter dimensions using the 14 dimension sensing datas of pca method (PCA) to selection.1# hair
The covariance matrix characteristic value of sensor parameters and variance contribution ratio are as shown in table 3 after motivation 14 normalization.
The covariance matrix characteristic value and variance contribution ratio (1# engine) of each sensor parameters of table 3
| Principal component | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
| Characteristic value | 0.4161 | 0.0241 | 0.0235 | 0.0173 | 0.0162 | 0.0140 | 0.0120 |
| Variance contribution ratio | 73% | 4% | 4% | 3% | 3% | 2% | 2% |
| Principal component | 8 | 9 | 10 | 11 | 12 | 13 | 14 |
| Characteristic value | 0.0112 | 0.0100 | 0.0095 | 0.0084 | 0.0072 | 0.0062 | 0.0057 |
| Variance contribution ratio | 2% | 2% | 2% | 1% | 1% | 1% | 0 |
As shown in Table 3, first principal component contains the data information of the overwhelming majority, selects first principal component in our current research
For characterizing the degenerate case of engine performance.Fig. 8 illustrates the first principal component of the performance parameter of 1# engine.
2.3 polygon matching primitives
It is illustrated by taking the 1# engine of test set as an example.Fig. 9, which gives, refers to engine number using first 4 of training set
According to the result estimated current engine (1# engine) service life to be predicted.
The analysis of 2.4 prediction results
The full longevity data building degeneration dictionary of 100 no longer valid engines for including using training set train_FD001,
Then it is randomly chosen 20 engines in test set test_FD001 and is predicted that engines ground true lifetime is in data
Collect in RUL_FD001, prediction result is as shown in table 4.
4 prediction result of table
| Serial number | True RUL | Predict RUL | Absolute error | Relative error |
| 1 | 112 | 125 | 13 | 0.12 |
| 2 | 98 | 90 | -8 | 0.08 |
| 3 | 69 | 54 | -15 | 0.22 |
| 4 | 82 | 63 | -19 | 0.23 |
| 5 | 91 | 66 | -25 | 0.27 |
| 6 | 93 | 71 | -22 | 0.24 |
| 7 | 91 | 73 | -18 | 0.20 |
| 8 | 111 | 86 | -25 | 0.23 |
| 9 | 97 | 69 | -28 | 0.29 |
| 10 | 107 | 82 | -25 | 0.23 |
| 11 | 83 | 103 | 20 | 0.24 |
| 12 | 84 | 89 | 5 | 0.06 |
| 13 | 50 | 50 | 0 | 0.00 |
| 14 | 87 | 76 | -11 | 0.13 |
| 15 | 57 | 72 | 15 | 0.26 |
| 16 | 111 | 105 | -6 | 0.05 |
| 17 | 113 | 88 | -25 | 0.22 |
| 18 | 145 | 112 | -33 | 0.23 |
| 19 | 119 | 105 | -14 | 0.12 |
| 20 | 66 | 70 | 4 | 0.06 |
| Mean value | -- | -- | -11 | 0.17 |
As known from Table 4, method proposed by the invention can accurately predict the remaining life of aero-engine very much, and
Life prediction has very important significance for the maintenance and maintenance of engine.
Claims (1)
1. a kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching, feature exist
In:
(1) its performance degradation mode is obtained by the gas circuit degraded data of aero-engine life-cycle, and uses more engines
Degraded data building performance degradation referring to dictionary；Firstly, there are the sensor parameters for obviously rising or falling trend to use for selection
To characterize the performance degradation of engine；Dimensionality reduction is carried out to data secondly, about subtracting method using dimension, obtains one-dimensional performance degradation
Curve；Finally, these refer to the Performance Degradation Data of engine according to certain specification storage, used convenient for later retrieval；
Engine data to be predicted pretreatment, selects sensor parameters identical with degeneration dictionary, and with same dimension reduction method
Carry out about subtracting for state parameter dimension；
(2) the performance degradation mode of aero-engine system is steadily characterized using the envelope polygon of Degradation path；Firstly,
The upper lower enveloping curve for referring to engine and engine Degradation path to be predicted is extracted, obtaining their degenerate polygon indicates shape
Formula；Secondly, matching engine degenerate polygon to be predicted in every degenerate polygon with reference to engine, it is overlapped them
Partial area is maximum；
(3) performance degradation between the two is quantified by reference to the overlapping area of engine and engine degenerate polygon to be predicted
The correlation of rule, and the overlapping area ratio using line segment length than equivalently calculating two polygons；
(4) using the true remaining life of reference engine as the estimated value of engine residual life to be predicted, according to faying surface
Product weights these life estimation values than generating similarity weight to obtain the remaining life of engine to be predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610543226.5A CN106169001B (en) | 2016-07-11 | 2016-07-11 | A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610543226.5A CN106169001B (en) | 2016-07-11 | 2016-07-11 | A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106169001A CN106169001A (en) | 2016-11-30 |
| CN106169001B true CN106169001B (en) | 2019-06-21 |
Family
ID=58064529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610543226.5A Active CN106169001B (en) | 2016-07-11 | 2016-07-11 | A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106169001B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107315396B (en) * | 2017-05-27 | 2019-06-11 | 中国电子科技集团公司第三十六研究所 | A kind of state monitor maintenance and predictive maintenance Combined maintenance method and system for planning |
| CN107357994B (en) * | 2017-07-14 | 2020-04-28 | 哈尔滨工业大学（威海） | Staged mining method for aircraft engine performance decline mode |
| CN108563806B (en) * | 2018-01-05 | 2019-06-14 | 哈尔滨工业大学（威海） | Engine air passage parameter long-range forecast method and system based on similitude |
| US11113168B2 (en) | 2018-03-09 | 2021-09-07 | Toyota Motor Engineering & Manufacturing North America, Inc. | Distributed architecture for fault monitoring |
| US10354462B1 (en) | 2018-04-06 | 2019-07-16 | Toyota Motor Engineering & Manufacturing North America, Inc. | Fault diagnosis in power electronics using adaptive PCA |
| US10650616B2 (en) | 2018-04-06 | 2020-05-12 | University Of Connecticut | Fault diagnosis using distributed PCA architecture |
| CN110135088B (en) * | 2019-05-20 | 2022-08-23 | 哈尔滨工业大学 | Early fault detection method for analog circuit based on normal envelope model of degradation characteristic parameters |
| CN110457731B (en) * | 2019-05-28 | 2023-04-25 | 中国航空工业集团公司上海航空测控技术研究所 | Method applied to vibration trend analysis of helicopter moving parts |
| CN110807257A (en) * | 2019-11-04 | 2020-02-18 | 中国人民解放军国防科技大学 | Method for predicting residual life of aircraft engine |
| CN110823575B (en) * | 2019-11-09 | 2021-03-16 | 北京工业大学 | Bearing life prediction method based on performance degradation dictionary structure and similarity |
| CN112348120A (en) * | 2020-12-01 | 2021-02-09 | 江苏南高智能装备创新中心有限公司 | Numerical control machine tool degradation track mode identification method and device |
| CN114326593B (en) * | 2021-12-16 | 2024-05-03 | 成都航天科工大数据研究院有限公司 | Cutter life prediction system and method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123447A (en) * | 2014-07-14 | 2014-10-29 | 南京信息工程大学 | Manufacturing system comprehensive evaluation method based on improved data envelopment analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7377179B2 (en) * | 2005-11-14 | 2008-05-27 | General Electric Company | System, method, and apparatus for wireless non-powered stress history and fatigue monitoring of a structure |
-
2016
- 2016-07-11 CN CN201610543226.5A patent/CN106169001B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123447A (en) * | 2014-07-14 | 2014-10-29 | 南京信息工程大学 | Manufacturing system comprehensive evaluation method based on improved data envelopment analysis |
Non-Patent Citations (2)
| Title |
|---|
| Envelope analysis and data-driven approaches to acoustic feature extraction for predicting the remaining useful life of rotating machinery;Darren F. Kavanagh 等;《IEEE Xplore》;20080512;全文 |
| 航空发动机的剩余寿命预测与健康状态评估;吴学海;《万方数据库学位论文库》;20140917;全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106169001A (en) | 2016-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106169001B (en) | A kind of aero-engine complete machine method for predicting residual useful life based on gas circuit performance parameter Graphic Pattern Matching | |
| CN106021826B (en) | One kind is based on aero-engine complete machine method for predicting residual useful life under operating mode's switch and the matched variable working condition of similitude | |
| CN110555479B (en) | Fault feature learning and classifying method based on 1DCNN and GRU fusion | |
| EP3477412B1 (en) | System fault isolation and ambiguity resolution | |
| US9779495B2 (en) | Anomaly diagnosis method and apparatus | |
| US8660980B2 (en) | Monitoring system using kernel regression modeling with pattern sequences | |
| US8620853B2 (en) | Monitoring method using kernel regression modeling with pattern sequences | |
| KR101316486B1 (en) | Error detection method and system | |
| CN106094570B (en) | A kind of aero-engine complete machine health evaluating method under variable working condition based on this distance of operating mode's switch and paddy | |
| Wang et al. | Research on the fault monitoring method of marine diesel engines based on the manifold learning and isolation forest | |
| CN107111309A (en) | Utilize the combustion gas turbine failure predication of supervised learning method | |
| CN104756029B (en) | A kind of system of the parts group of monitoring device | |
| Sun et al. | A non-probabilistic metric derived from condition information for operational reliability assessment of aero-engines | |
| Behera et al. | Ensemble trees learning based improved predictive maintenance using IIoT for turbofan engines | |
| CN114282579A (en) | Aviation bearing fault diagnosis method based on variational modal decomposition and residual error network | |
| Armstrong et al. | Implementation of an integrated on-board aircraft engine diagnostic architecture | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| Liang et al. | A degradation degree considered method for remaining useful life prediction based on similarity | |
| Zhiyong et al. | Prognostics uncertainty reduction by right-time prediction of remaining useful life based on hidden Markov model and proportional hazard model | |
| Gkerekos et al. | Ship machinery condition monitoring using vibration data through supervised learning | |
| CN105408828B (en) | To being used to detecting the method that the reference point of engine abnormity estimated and the data handling system for implementing this method on curve | |
| Bect et al. | Identification of abnormal events by data monitoring: Application to complex systems | |
| Viale et al. | Least squares smoothed k-nearest neighbors online prediction of the remaining useful life of a NASA turbofan | |
| CN109308484A (en) | Aero-engine multiclass failure minimum risk diagnostic method and device | |
| Hsu et al. | A comparison of residual-based methods on fault detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |